Künstliche Intelligenz in der laryngealen Endoskopie

Abstract

The application of artificial intelligence (AI) in medical imaging allows the rapid and complex analysis of endoscopic image material. Laryngeal endoscopy has several applications with its variants, such as video stroboscopy and high-speed video endoscopy. AI can enhance image quality, detect lesions through object detection, and quantify vocal fold vibration behavior through glottal area identification. The application of AI-assisted endoscopy systems simplifies diagnosis and therapy monitoring and supports the medical staff in their tasks.

Kernaussagen

• Künstliche Intelligenz, vor allem das Deep Learning, erlaubt eine automatisierte Bildanalyse.

• Verschiedene Verfahren der laryngealen Endoskopie können von KI profitieren.

• Anwendungsgebiete sind die Verbesserung der Bildqualität, die Anomalie-Erkennung, sowie die Quantifizierung des Schwingungsverhaltens der Stimmlippen.

• Im Falle der Hochgeschwindigkeits-Videoendoskopie (HSV) macht die Anwendung erst mit KI Sinn.

• Durch umfangreiche Studien können Ängste abgebaut und neue Möglichkeiten erschlossen werden.

Schlüsselwörter

KI - maschinelles Lernen - Bildverarbeitung - laryngeale Endoskopie

Key words

Artificial intelligence - laryngeal endoscopy - medical imaging

Publication History

Article published online:
05 September 2023

• Literatur

• 1 Briganti G, Le Moine O. Artificial intelligence in medicine: today and tomorrow. Front Med 2020; 7: 27
• 2 Castiglioni I, Rundo L, Codari M. et al. AI applications to medical images: From machine learning to deep learning. Physica Medica 2021; 83: 9-24
• 3 He K, Gkioxari G, Dollár P. et al. Mask R-CNN. Proceedings of the IEEE international conference on computer vision. 2017. 2961-2969
• 4 Rosen CA, Murry T. Diagnostic laryngeal endoscopy. Otolaryngol Clin North Am 2000; 33: 751-757
• 5 Woo P. Quantification of videostrobolaryngoscopic findings-measurements of the normal glottal cycle. Laryngoscope 1996; 106: 1-27
• 6 Schützenberger A, Kunduk M, Döllinger M. et al. Laryngeal High-Speed Videoendoscopy: Sensitivity of Objective Parameters towards Recording Frame Rate. Biomed Res Int 2016; 2016
• 7 Lohscheller J, Eysholdt U, Toy H. et al. Phonovibrography: Mapping High-Speed Movies of Vocal Fold Vibrations Into 2-D Diagrams for Visualizing and Analyzing the Underlying Laryngeal Dynamics. IEEE Transactions on Medical Imaging 2008; 27: 300-309
• 8 Żurek M, Jasak K, Niemczyk K. et al. Artificial Intelligence in Laryngeal Endoscopy: Systematic Review and Meta-Analysis. JCM 2022; 11: 2752
• 9 Kist AM, Gómez P, Dubrovskiy D. et al. A Deep Learning Enhanced Novel Software Tool for Laryngeal Dynamics Analysis. J Speech Lang Hear Res 2021; 64 : 1889-1903
• 10 Gómez P, Semmler M, Schützenberger A. et al. Low-light image enhancement of high-speed endoscopic videos using a convolutional neural network. Med Biol Eng Comput 2019; 57: 1451-1463
• 11 Azam MA, Sampieri C, Ioppi A. et al. Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real‐Time Laryngeal Cancer Detection. Laryngoscope 2022; 132: 1798-1806
• 12 Kist AM, Döllinger M. Efficient Biomedical Image Segmentation on EdgeTPUs at Point of Care. IEEE Access 2020; 8: 139356-139366
• 13 Andrade-Miranda G, Stylianou Y, Deliyski DD. et al. Laryngeal Image Processing of Vocal Folds Motion. Applied Sciences 2020; 10: 1556
• 14 Gómez P, Kist AM, Schlegel P. et al. BAGLS, a multihospital Benchmark for Automatic Glottis Segmentation. Scientific Data 2020; 7: 186
• 15 Kist AM, Breininger K, Dörrich M. et al. A single latent channel is sufficient for biomedical glottis segmentation. Sci Rep 2022; 12: 14292
• 16 Döllinger M, Schraut T, Henrich LA. et al. Re-Training of Convolutional Neural Networks for Glottis Segmentation in Endoscopic High-Speed Videos. Appl Sci 2022; 12: 9791
• 17 Schlegel P, Stingl M, Kunduk M. et al. Dependencies and ill-designed parameters within high-speed videoendoscopy and acoustic signal analysis. J Voice 2019; 33: 811-e1
• 18 Inwald EC, Döllinger M, Schuster M. et al. Multiparametric analysis of vocal fold vibrations in healthy and disordered voices in high-speed imaging. J Voice 2011; 25: 576-590
• 19 Kist AM, Dürr S, Schützenberger A. et al. OpenHSV: an open platform for laryngeal high-speed videoendoscopy. Sci Rep 2021; 11: 13760